Error: 'nx >= k' failed: Number of training points (77) should be at least as large as number of clusters (256) #30
Description
按照https://github.com/tpoisonooo/ROGRAG/blob/main/docs/en/doc_how_to_run.md 运行 python3 -m huixiangdou.pipeline.store 时报错
Traceback (most recent call last):
File "/app/huangqixing/miniconda3/envs/test/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/app/huangqixing/miniconda3/envs/test/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/app/huangqixing/ROGRAG-main/huixiangdou/pipeline/store.py", line 438, in
loop.run_until_complete(store.init(files=files, args=args))
File "/app/huangqixing/miniconda3/envs/test/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/app/huangqixing/ROGRAG-main/huixiangdou/pipeline/store.py", line 325, in init
await self.build_knowledge(files=documents)
File "/app/huangqixing/ROGRAG-main/huixiangdou/pipeline/store.py", line 186, in build_knowledge
entityDB.save(folder_path=os.path.join(self.work_dir, 'db_kag_entity'),
File "/app/huangqixing/ROGRAG-main/huixiangdou/primitive/faiss.py", line 303, in save
self.save_local(folder_path=folder_path,
File "/app/huangqixing/ROGRAG-main/huixiangdou/primitive/faiss.py", line 244, in save_local
index.train(all_features) # 先训练索引
File "/app/huangqixing/miniconda3/envs/test/lib/python3.10/site-packages/faiss/init.py", line 280, in replacement_train
self.train_c(n, swig_ptr(x))
File "/app/huangqixing/miniconda3/envs/test/lib/python3.10/site-packages/faiss/swigfaiss.py", line 5998, in train
return _swigfaiss.IndexHNSWPQ_train(self, n, x)
RuntimeError: Error in void faiss::Clustering::train_encoded(faiss::Clustering::idx_t, const uint8_t*, const faiss::Index*, faiss::Index&, const float*) at /project/faiss/faiss/Clustering.cpp:283: Error: 'nx >= k' failed: Number of training points (77) should be at least as large as number of clusters (256)